© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16368
    Prev
    Next
    INDEX
    Explanations

    code blocks that do not contain letters, digits, or parenthesis

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.76
    hed
    -0.47
    ANTLR
    -0.46
    head
    -0.45
     Mer
    -0.44
    archiviato
    -0.44
    tagHelper
    -0.44
    pp
    -0.44
    abu
    -0.44
    isma
    -0.43
    POSITIVE LOGITS
    seamnă
    0.79
     contextLoads
    0.71
     auroit
    0.67
     correctes
    0.65
    findpost
    0.64
     يتيمه
    0.63
     feroit
    0.62
     vertes
    0.61
     avoient
    0.61
     protoimpl
    0.61
    Activations Density 0.204%

    No Known Activations